Documentation ¶
Overview ¶
Package dist provides differentiatable distribution models. The package is automatically differentiated by deriv during build.
Index ¶
Constants ¶
This section is empty.
Variables ¶
View Source
var Beta beta
Beta distribution, singleton instance.
View Source
var Expon expon
Exponential distribution, singleton instance.
View Source
var Gamma gamma
Gamma distribution, singleton instance.
View Source
var Normal normal
Normal distribution, singleton instance.
View Source
var SoftMax func(x, p []float64)
Outside of differentiated context, SoftMax can be used without distribution.
Functions ¶
This section is empty.
Types ¶
type Categorical ¶ added in v0.5.1
type Categorical struct {
N int // number of categories
}
the categorical distribution
func (Categorical) Logp ¶ added in v0.5.1
func (dist Categorical) Logp( alpha []float64, y float64, ) float64
Logp computes logpdf of a single observation.
func (Categorical) Logps ¶ added in v0.5.1
func (dist Categorical) Logps( alpha []float64, ys ...float64, ) float64
Logps computes logpdf of a vector of observations.
func (Categorical) Observe ¶ added in v0.5.1
func (dist Categorical) Observe(x []float64) float64
Observe implements the Model interface
type Dirichlet ¶
type Dirichlet struct {
N int // number of dimensions
}
Dirichlet distribution
Click to show internal directories.
Click to hide internal directories.